© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 362
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Rod" with varying endings (e.g., Rod, Roddericks, Rodgers)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    893
    +0.11
    0.4%
    1339
    +0.09
    0.3%
    506
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    893
    +0.11
    0.03
    1120
    +0.09
    0.03
    1614
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.99
    
    -0.70
    /*
    -0.63
    ⓧ
    -0.61
     kív
    -0.60
    LabelTagHelper
    -0.59
     прі
    -0.59
    فى
    -0.56
     endorse
    -0.56
     прий
    -0.55
    POSITIVE LOGITS
     Rod
    1.98
    Rod
    1.77
     ROD
    1.40
     ekos
    1.21
     hcm
    1.19
     kafe
    1.18
     kasa
    1.17
     obé
    1.17
     keramik
    1.17
     mef
    1.17
    Activations Density 0.265%

    No Known Activations